The Agent Skills Directory

[SAFE]: The skill defines a logical workflow for artifact evaluation using clear dimensions and stop conditions. No prompt injection or behavior override attempts were detected.
[SAFE]: The script scripts/rubric-scorecard.py uses safe JSON loading and numeric calculation. It does not contain dynamic code execution (eval/exec), subprocess calls, or unauthorized file system access outside of specified arguments.
[SAFE]: No credential exposure, data exfiltration patterns, or network operations were identified in the skill instructions or scripts.
[SAFE]: References to external tools and portability steps are consistent with standard development practices and target well-known, trusted platforms.

agentic-eval